1、聚类出所有目标的bounding box,提取目标的bounding box
2、获得bounding box的宽高信息(将左上角坐标,右下角坐标装换成宽高)
3、初始化k个anchor box,通过在所有的bounding boxes中随机选取k个值作为k个anchor boxes的初始值
4、计算每个bounding box与每个anchor box的iou值
5、分类操作。计算每个anchor box与bounding box的误差值,将误差最小的bounding box分类到anchor box,即每一个bounding box 属于 anchor box
6、anchor box 更新。将属于每一类anchor box的bouding box 的宽高求中值,宽高作为anchor box新的宽高
7、重复4-6步,直到anchor box类中的bouding box 不在更新
8、计算anchor boxes精确度,每个bounding box选取其最高的那个IOU值(代表其属于某一个anchor box类),然后求所有bounding box该IOU值的平均值也即最后的精确度值
import numpy as np
import matplotlib.pyplot as plt
class YOLO_Kmeans:
def __init__(self, cluster_number, filename):
self.cluster_number = cluster_number
self.filename = "train.txt"
def iou(self, boxes, clusters): # 1 box -> k clusters
n = boxes.shape[0]
k = self.cluster_number
# print(clusters)
# print( boxes[:, 0],boxes[:, 1])
box_area = boxes[:, 0] * boxes[:, 1] # 宽乘高
box_area = box_area.repeat(k) #将每个box的面积重复k次,构成一个1行k列的数组
box_area = np.reshape(box_area, (n, k)) #把box_area整理成n行k列的形式
# print(box_area)
cluster_area = clusters[:, 0] * clusters[:, 1] # 宽乘高 [10560 11088 444686 612942]
# print(cluster_area)
cluster_area = np.tile(cluster_area, [1, n]) # y轴不变,x轴复制 (1, 15172)
# print(cluster_area)
cluster_area = np.reshape(cluster_area, (n, k)) # 把cluster_area整理成n行k列的形式
# print(cluster_area)
box_w_matrix = np.reshape(boxes[:, 0].repeat(k), (n, k))
# print(box_w_matrix)
cluster_w_matrix = np.reshape(np.tile(clusters[:, 0], (1, n)), (n, k))
# print(cluster_w_matrix)
min_w_matrix = np.minimum(cluster_w_matrix, box_w_matrix)
box_h_matrix = np.reshape(boxes[:, 1].repeat(k), (n, k))
cluster_h_matrix = np.reshape(np.tile(clusters[:, 1], (1, n)), (n, k))
min_h_matrix = np.minimum(cluster_h_matrix, box_h_matrix)
inter_area = np.multiply(min_w_matrix, min_h_matrix)
result = inter_area / (box_area + cluster_area - inter_area)
# print(result.shape) #n行k列
return result
def kmeans(self, boxes, k, dist=np.median):
"""
:param boxes: boxes = all_boxes (3793, 2)
:param k:
:param dist:求宽和高的均值
:return:聚类后宽和高的结果
"""
box_number = boxes.shape[0] # 盒子数量
distances = np.empty((box_number, k)) # (3793, 9)
last_nearest = np.zeros((box_number,)) #(3793,)
np.random.seed()
clusters = boxes[np.random.choice(
box_number, k, replace=False)] # init k clusters 按行随机取k个不同的box_number
# print(clusters)
while True:
# distance是一个n行k列的小于1的数组,比较每一行提出来最小的一个,意义是每行中选出一个最合适的聚类中心
# 比如第一个box和第3个距离最小,第二个和第4个聚类中心距离最小。。。。。。[3,4,5,0,1,。。。。。。。4]
distances = 1 - self.iou(boxes, clusters)
# print(distances.shape)
current_nearest = np.argmin(distances, axis=1)# 在行上找最小索引
# print(current_nearest)#[2 1 3 ... 2 0 0]
# break
if (last_nearest == current_nearest).all(): #判断两个数组是否相等
break # clusters won't change
# 更换聚类中心
for cluster in range(k):
"""
找出k个anchor的宽和高
current_nearest行上的索引
boxes[current_nearest == cluster] 取出需要聚类的盒子
clusters[cluster] = dist( # update clusters
boxes[current_nearest == cluster], axis=0)求出平局宽和高
"""
clusters[cluster] = dist( # update clusters
boxes[current_nearest == cluster], axis=0) # 找出第一种box的宽和高
last_nearest = current_nearest
return clusters
def result2txt(self, data):
f = open("yolo_anchors.txt", 'w')
row = np.shape(data)[0] #k个anchor
for i in range(row):
if i == 0:
x_y = "%d,%d" % (data[i][0], data[i][1])
else:
x_y = ", %d,%d" % (data[i][0], data[i][1])
f.write(x_y)
f.close()
def txt2boxes(self):
"""
:return: [[170 58]
[719 747]
[166 63]]
"""
f = open(self.filename, 'r')
dataSet = []
for line in f:
infos = line.split(" ") # 按空格分隔
length = len(infos)
for i in range(1, length):
width = int(infos[i].split(",")[2]) - \
int(infos[i].split(",")[0])
height = int(infos[i].split(",")[3]) - \
int(infos[i].split(",")[1])
dataSet.append([width, height])
result = np.array(dataSet)
f.close()
return result
def avg_iou(self, boxes, clusters):
accuracy = np.mean([np.max(self.iou(boxes, clusters), axis=1)]) # 按行取最大值再求均值
return accuracy
def txt2clusters(self):
"""
result.T[0, None]取第一列元素并转置
np.lexsort(result.T[0, None]对元素排序,返回标号
result[np.lexsort(result.T[0, None])]重新排序
:return:
"""
all_boxes = self.txt2boxes()
# print(all_boxes)
result = self.kmeans(all_boxes, k=self.cluster_number)
result = result[np.lexsort(result.T[0, None])]
self.result2txt(result)
# print(result)
# print("K anchors:\n {}".format(result))
res = "{:.2f}%".format(
self.avg_iou(all_boxes, result) * 100)
# res = self.avg_iou(all_boxes, result)
print("Accuracy: {:.2f}%".format(
self.avg_iou(all_boxes, result) * 100))
return res
if __name__ == '__main__':
# cluster_number = 9
filename = "train.txt"
y_ = []
for i in range(1,13):
kmeans = YOLO_Kmeans(i, filename)
accuracy = kmeans.txt2clusters()
y_.append(accuracy)
# print(kmeans.txt2clusters())
print(y_)